SECAI Core · phase 1 of 15 · noun
Unsupervised learning
A category of machine learning that does not use labeled data to predict outcomes, but instead relies on the computer to sort out patterns and similarities in the larger dataset.
The Explain card
- Plain English
- Unsupervised learning gives the machine data without labels and lets it find the patterns, groups and similarities on its own.
- Example
- A security team feeds raw authentication logs into a clustering algorithm. It groups logins into natural clusters, and one small odd cluster turns out to be a service account being used from three countries at once.
- Why it matters
- Unsupervised models surface what is unusual, which makes them great for anomaly detection, but they also find patterns nobody asked for, including sensitive groupings that raise privacy and bias questions.
- Hook
- No answer key, just "sort this pile and tell me what looks odd."
Word knowledge
How the word is built, where it came from, and what it sits beside in memory.
In a sentence
The SIEM ran unsupervised learning on last week's DNS queries and grouped the lookups so the analyst could inspect the small clusters.
Why these words
- unsupervised English un- (not) plus Latin supervisus, overseen, from supervidere, to look over marks the training as happening with no overseer, the un- that opposes supervised
- learning Old English leornung, the act of getting knowledge names the classroom activity the phrase assigns to a machine
Where it came from
- Origin
- English compound from un- (not) plus Latin supervisus (overseen, from super, over, and videre, to see) and Old English leornung (the act of getting knowledge)
- Entered the language
- 1960s
- What changed
- Unsupervised had meant a person working with no overseer since the late 1700s. Learning had meant a person acquiring knowledge. Pattern-recognition labs in the 1960s joined them as the name for training without a teacher, and the pair became the ordinary label for that family of methods.
How it is spelled
- Pattern
- un- is the native English prefix for not, written solid with the stem
- Pattern
- super- keeps its Latin spelling and its sense of over
- Pattern
- -vise from Latin videre always takes s, never z
- Pattern
- -ed marks the past participle used as an adjective
- Pattern
- -ing turns a verb into a noun of activity
- Breaks the pattern
- the noun phrase stays two words; the hyphen appears only when it modifies another noun
- Breaks the pattern
- supervise is not an -ize verb; the s is from vis, see, so American spelling still writes s
Spelled like
- unexpected
- untrained
- revise
- supervisor
Broken into chunks
-
un
- unexpected
- unpaid
- untrained
-
super
- superhuman
- superintendent
- superimpose
-
vise
- revise
- advise
- televise
-
ed
- trained
- marked
- unexpected
-
learn
- learner
- unlearn
- relearn
-
ing
- training
- computing
- reasoning
What it sits beside
Same subject
Same shape
- supervised learning
- self-supervised learning
- semi-supervised learning
- reinforcement learning
Learning compounds
Un- family
- unexpected
- untrained
- unpaid
Training regimes
- supervised learning
- reinforcement learning
- self-supervised learning
Where it sits in the deck
Phase 1: What AI Is: Core Concepts and Paradigms
You cannot secure, govern, or attack something you cannot define — establish what AI actually is before any other concept can land.